@fastino-ai/pioneer-cli 0.2.0 → 0.2.2

package/.claude/settings.local.json

@@ -0,0 +1,11 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(echo:*)",
+      "Bash(bun run build:*)",
+      "WebFetch(domain:localhost)",
+      "Bash(bun run:*)",
+      "Bash(cat:*)"
+    ]
+  }
+}

package/README.md

@@ -1,6 +1,6 @@
 # Pioneer CLI
 
-Command-line interface for the Pioneer AI training platform with an intelligent chat agent.
+Command-line interface for the Pioneer AI training platform.
 
 ```
 ██████╗ ██╗ ██████╗ ███╗   ██╗███████╗███████╗██████╗ 
@@ -11,23 +11,15 @@ Command-line interface for the Pioneer AI training platform with an intelligent
 ╚═╝     ╚═╝ ╚═════╝ ╚═╝  ╚═══╝╚══════╝╚══════╝╚═╝  ╚═╝
 ```
 
-## Features
-
-- **Interactive Chat Agent**: Claude Code-like experience with bash execution, file operations, and code sandbox
-- **ML Integrations**: Modal.com for serverless GPU compute, Weights & Biases for experiment tracking
-- **Self-Evolution**: Autonomous self-improvement with feedback collection and model fine-tuning
-- **Budget Management**: Token, time, and cost tracking with configurable limits
-- **Pioneer Platform**: Full access to Pioneer AI training platform APIs
-
 ## Installation
 
-### Quick Install (requires Bun)
+### npm 
 
 ```bash
-curl -fsSL https://pioneer.ai/install.sh | sh
-```
+npm install -g @fastino-ai/pioneer-cli
 
-### Manual Install
+```
+### Manual Install (requires Bun)
 
 ```bash
 # Install Bun if needed
@@ -42,117 +34,18 @@ bun install
 bun run src/index.tsx --help
 ```
 
-## Chat Agent
-
-The chat agent provides a Claude Code-like experience with powerful capabilities:
-
-### Starting the Chat
+### Quick Install (coming soon)
 
 ```bash
-# Interactive chat mode
-pioneer chat
-
-# With specific provider/model
-pioneer chat --provider anthropic --model claude-sonnet-4-20250514
-pioneer chat --provider openai --model gpt-4o
-
-# Run a single command
-pioneer chat --message "Create a Python script that analyzes CSV files"
-```
-
-### Capabilities
-
-| Capability | Description |
-|------------|-------------|
-| **Bash Execution** | Run shell commands, install packages, manage system |
-| **File Operations** | Read, write, edit, search files and directories |
-| **@ File References** | Reference local files with `@path` syntax like Claude Code |
-| **Code Sandbox** | Execute Python, JavaScript, TypeScript, Bash, Ruby, Go in isolation |
-| **Modal.com** | Deploy ML workloads on serverless GPUs |
-| **Weights & Biases** | Track experiments and metrics |
-| **Model Training** | Fine-tune models with LoRA or full training |
-
-### @ File References
-
-Reference local files and directories using the `@` syntax, similar to Claude Code:
-
-```bash
-# Reference a single file
-> Explain @src/index.tsx
-
-# Reference multiple files
-> Compare @package.json and @tsconfig.json
-
-# Reference a directory (shows tree structure)
-> What's in @src/
-
-# Relative paths work too
-> Look at @./config.ts and @../other-project/file.ts
+curl -fsSL https://pioneer.ai/install.sh | sh
 ```
 
-When you use `@path`, the file contents are automatically:
-1. Read from your filesystem
-2. Included in the context sent to the LLM
-3. Displayed with a checkmark indicator
-
-This allows the agent to see and understand your code without manually reading files.
-
-### Chat Commands
-
-| Command | Description |
-|---------|-------------|
-| `/help` | Show available commands |
-| `/clear` | Clear conversation history |
-| `/tools` | List available tools |
-| `/budget` | Show token/cost usage |
-| `/exit` | Exit the chat |
-
-## Environment Variables
+## Usage
 
 ```bash
-# LLM Provider Keys (required for chat)
-export ANTHROPIC_API_KEY="your-anthropic-key"
-export OPENAI_API_KEY="your-openai-key"
-
-# Pioneer Platform
-export PIONEER_API_URL="https://agent.pioneer.ai"
-export PIONEER_API_KEY="your-pioneer-key"
-
-# ML Integrations (optional)
-export MODAL_TOKEN_ID="your-modal-token-id"
-export MODAL_TOKEN_SECRET="your-modal-token-secret"
-export WANDB_API_KEY="your-wandb-key"
-```
+# Show help
+pioneer --help
 
-## Configuration
-
-Configuration is stored in `~/.pioneer/config.json`:
-
-```json
-{
-  "apiKey": "your-pioneer-api-key",
-  "baseUrl": "https://agent.pioneer.ai",
-  "agent": {
-    "provider": "anthropic",
-    "model": "claude-sonnet-4-20250514"
-  },
-  "budget": {
-    "maxTokens": 100000,
-    "maxCost": 1.0,
-    "maxTime": 3600
-  },
-  "ml": {
-    "wandb": {
-      "project": "my-project",
-      "entity": "my-team"
-    }
-  }
-}
-```
-
-## Pioneer Platform Usage
-
-```bash
 # Authentication
 pioneer auth login       # Enter API key interactively
 pioneer auth logout      # Clear stored API key
@@ -178,57 +71,114 @@ pioneer model delete <id>
 pioneer model download <id>
 ```
 
-## Architecture
+## End-to-End Example
+
+This example shows the complete workflow from generating a dataset to training a model.
+
+### Step 1: Generate a Dataset
+
+Generate a NER (Named Entity Recognition) dataset for medical text:
+
+```bash
+# Save locally to ./datasets/ (default)
+pioneer dataset generate ner \
+  --labels "DISEASE,SYMPTOM,TREATMENT,MEDICATION" \
+  --num 50 \
+  --domain "Medical clinical notes and patient records" \
+  --name "medical-ner"
+
+# Or save to remote database
+pioneer dataset generate ner \
+  --labels "DISEASE,SYMPTOM,TREATMENT,MEDICATION" \
+  --num 50 \
+  --domain "Medical clinical notes and patient records" \
+  --save true \
+  --name "Medical NER Dataset"
+```
+
+Or generate a classification dataset for sentiment analysis:
+
+```bash
+pioneer dataset generate classification \
+  --labels "positive,negative,neutral" \
+  --num 200 \
+  --domain "Customer product reviews" \
+  --name "sentiment"
+```
+
+### Step 2: View Your Datasets
+
+```bash
+# List all datasets (both remote and local ./datasets/*.json)
+pioneer dataset list
+
+# Get details for a remote dataset
+pioneer dataset get <dataset-id>
+
+# Analyze dataset statistics
+pioneer dataset analyze <dataset-id>
+```
+
+### Step 3: Create a Training Job
+
+Start training with one or more datasets:
+
+```bash
+pioneer job create \
+  --model-name "Medical NER Model v1" \
+  --dataset-ids "<dataset-id>" \
+  --base-model "fastino/gliner2-base-v1" \
+  --epochs 10
+```
+
+### Step 4: Monitor Training Progress
 
+```bash
+# List all training jobs
+pioneer job list
+
+# Check job status
+pioneer job get <job-id>
+
+# View training logs
+pioneer job logs <job-id>
 ```
-src/
-├── index.tsx          # CLI entry point and routing
-├── config.ts          # Configuration management
-├── api.ts             # Pioneer platform API client
-├── chat/
-│   └── ChatApp.tsx    # Interactive chat UI
-├── agent/
-│   ├── Agent.ts       # Main agent orchestrator
-│   ├── LLMClient.ts   # OpenAI/Anthropic client
-│   ├── ToolRegistry.ts # Tool management
-│   ├── BudgetManager.ts # Budget tracking
-│   └── types.ts       # Type definitions
-├── tools/
-│   ├── bash.ts        # Shell command execution
-│   ├── filesystem.ts  # File operations
-│   ├── sandbox.ts     # Code sandbox
-│   ├── modal.ts       # Modal.com integration
-│   ├── wandb.ts       # W&B integration
-│   └── training.ts    # Model training
-└── evolution/
-    ├── EvolutionEngine.ts  # Self-improvement loop
-    ├── FeedbackCollector.ts # Feedback storage
-    ├── EvalRunner.ts       # Evaluation framework
-    └── ModelTrainer.ts     # Fine-tuning
+
+### Step 5: Use Your Trained Model
+
+Once training completes:
+
+```bash
+# List trained models
+pioneer model list trained
+
+# Download the trained model
+pioneer model download <job-id>
 ```
 
-## Self-Evolution System
+## Configuration
+
+The CLI stores configuration in `~/.pioneer/config.json`.
+
+### Environment Variables
 
-The agent can autonomously improve itself within budget constraints:
+| Variable | Description |
+|----------|-------------|
+| `PIONEER_API_URL` | API base URL (default: `https://api.fastino.ai`) |
+| `PIONEER_API_KEY` | API key (overrides saved key) |
 
-1. **Feedback Collection**: Records successful/failed interactions
-2. **Evaluation**: Runs test cases to measure performance
-3. **Training**: Fine-tunes models based on feedback
-4. **Budget-Aware**: Respects token/time/cost limits
+## Authentication
 
-```typescript
-import { EvolutionEngine } from './evolution';
+The CLI first needs to validate your API key. To get one, go to https://api.fastino.ai/api-keys .
 
-const engine = new EvolutionEngine({
-  targetScore: 0.9,
-  maxIterations: 10,
-  budgetPerIteration: {
-    maxTokens: 50000,
-    maxCost: 0.50,
-  },
-});
+```bash
+# Login with API key
+pioneer auth login
+# Enter your API key when prompted
 
-await engine.evolve(agent);
+# Or set via environment
+export PIONEER_API_KEY="your-api-key"
+pioneer dataset list
 ```
 
 ## Development
@@ -238,7 +188,6 @@ cd pioneer
 bun install
 bun run dev          # Hot reload
 bun run typecheck    # Type checking
-bun run chat         # Start chat agent
 ```
 
 ## Tech Stack
@@ -246,9 +195,6 @@ bun run chat         # Start chat agent
 - **Runtime**: [Bun](https://bun.sh)
 - **UI**: [Ink](https://github.com/vadimdemedes/ink) (React for CLI)
 - **Language**: TypeScript
-- **LLMs**: Anthropic Claude, OpenAI GPT
-- **ML Compute**: [Modal](https://modal.com)
-- **Experiment Tracking**: [Weights & Biases](https://wandb.ai)
 
 ## License